© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17904
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sha" and its variations in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.92
    ്ട
    -0.89
    yszer
    -0.77
    ſelf
    -0.76
    Porte
    -0.73
    MTL
    -0.73
     Morley
    -0.73
     Yorke
    -0.73
    MatInputModule
    -0.72
    üst
    -0.72
    POSITIVE LOGITS
     Sha
    1.61
    Sha
    1.56
    sha
    1.55
     sha
    1.39
     SHA
    1.30
     Shapiro
    1.23
    SHA
    1.13
     Shaffer
    1.12
     Shasta
    0.93
     Shao
    0.86
    Activations Density 0.008%

    No Known Activations